Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    an informal blog post about self-help and feelings

    oai_token-act-pair · gemini-2.0-flash

    positive emojis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.07
     مرئيه
    -0.77
     allAfrica
    -0.69
     ligiloj
    -0.66
    tvguidetime
    -0.65
    ConstraintMaker
    -0.64
    ThroughAttribute
    -0.64
    曖昧さ回避
    -0.63
    /*++
    -0.62
    TargetException
    -0.61
    POSITIVE LOGITS
    😊
    0.56
    💐
    0.52
    😍
    0.52
    👌
    0.52
     😊
    0.51
    👍
    0.50
    🌷
    0.49
    iastical
    0.49
    🎉
    0.49
    😁
    0.49
    Act Density 2.435%

    No Known Activations